Random Forest for Human Daily Activity Recognition
Authors:
- Nurul Retno NurwulanNNNurul Retno Nurwulan
- Gjergji SelamajGSGjergji Selamaj
Open Access
- 1 October 2020
- conference paper
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1655 (1)
Abstract
Machine learning classifiers are often used to evaluate the predicting accuracy of human activity recognition. This study aimed to evaluate the performance of random forest (RF) compared to other classifiers with considering the time taken to build the models. Human activity daily living data, namely walking, walking upstairs, walking downstairs, sitting, standing, and lying down were collected from smartphone-based accelerometer with sampling frequency of 50Hz. The dataset was evaluated using artificial neural network (ANN), k-nearest neighbors (KNN), linear discriminant analysis (LDA), naïve Bayes (NB), support vector machine (SVM), and random forest (RF). The results of the study showed that RF indeed predicted the activities with the highest accuracy. However, the time taken to build the models using RF was the second-longest after ANN.Keywords
This publication has 12 references indexed in Scilit:
- Possibility of Using Entropy Method to Evaluate the Distracting Effect of Mobile Phones on PedestriansEntropy, 2016
- Comparison of Frequency Domain and Time-Domain Methods for Aeromechanical AnalysisInternational Journal of Rotating Machinery, 2016
- A Survey on Human Activity Recognition using Wearable SensorsIEEE Communications Surveys & Tutorials, 2012
- Human action segmentation and recognition via motion and shape analysisPattern Recognition Letters, 2012
- Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forestsBMC Research Notes, 2011
- Removing Batch Effects in Analysis of Expression Microarray Data: An Evaluation of Six Batch Adjustment MethodsPLOS ONE, 2011
- Human activity recognition in pervasive health-care: Supporting efficient remote collaborationJournal of Network and Computer Applications, 2008
- Activity-Aware Computing for HealthcareIEEE Pervasive Computing, 2008
- Implementation of a Real-Time Human Movement Classifier Using a Triaxial Accelerometer for Ambulatory MonitoringIEEE Transactions on Information Technology in Biomedicine, 2006
- Support-vector networksMachine Learning, 1995